Benchmarking Neural Networks Activation Functions for Cancer Detection

Miguel Angel Quiroz Martinez; Josue Ricardo Borja Vernaza; Daniel Humberto Plua Moran; Maikel Yelandi Leyva Vazquez

doi:10.1007/978-3-030-85540-6_110

Benchmarking Neural Networks Activation Functions for Cancer Detection

Miguel Angel Quiroz Martinez, Josue Ricardo Borja Vernaza, Daniel Humberto Plua Moran, Maikel Yelandi Leyva Vazquez

Research Group in Artificial Intelligence and Facial Recognition (GIIAR)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The choice of the most suitable activation functions for artificial neural networks significantly affects training time and task performance. Breast cancer detection is currently based on the use of neural networks and their selection is an element that affects performance. In the present work, reference information on activation functions in neural networks was analyzed. Exploratory research, comprehensive reading, stepwise approach, and deduction were applied as a method. It resulted in phases of comparative evaluation inactivation functions, a quantitative and qualitative comparison of activation functions, and a prototype of neural network algorithm with activation function to detect cancer; It was concluded that the final results put as the best option to use ReLU for early detection of cancer.

Original language	English
Title of host publication	Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET
Subtitle of host publication	Future Systems IHIET-FS 2021
Editors	Tareq Ahram, Redha Taiar
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	867-873
Number of pages	7
ISBN (Print)	9783030855390
DOIs	https://doi.org/10.1007/978-3-030-85540-6_110
State	Published - 2022
Event	5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021 - Virtual, Online Duration: 27 Aug 2021 → 29 Aug 2021

Publication series

Name	Lecture Notes in Networks and Systems
Volume	319

Conference

Conference	5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021
City	Virtual, Online
Period	27/08/21 → 29/08/21

Bibliographical note

Funding Information:
This work has been supported by the GIIAR research group and the Universidad Polit?cnica Salesiana.

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Activation functions
Benchmarking
Cancer detection
Neural networks

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-85540-6_110

Cite this

Martinez, M. A. Q., Vernaza, J. R. B., Moran, D. H. P., & Vazquez, M. Y. L. (2022). Benchmarking Neural Networks Activation Functions for Cancer Detection. In T. Ahram, & R. Taiar (Eds.), Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET: Future Systems IHIET-FS 2021 (pp. 867-873). (Lecture Notes in Networks and Systems; Vol. 319). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-85540-6_110

Martinez, Miguel Angel Quiroz ; Vernaza, Josue Ricardo Borja ; Moran, Daniel Humberto Plua et al. / Benchmarking Neural Networks Activation Functions for Cancer Detection. Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET: Future Systems IHIET-FS 2021. editor / Tareq Ahram ; Redha Taiar. Springer Science and Business Media Deutschland GmbH, 2022. pp. 867-873 (Lecture Notes in Networks and Systems).

@inproceedings{1f4ecaccb65d48609de377c09822b6ea,

title = "Benchmarking Neural Networks Activation Functions for Cancer Detection",

abstract = "The choice of the most suitable activation functions for artificial neural networks significantly affects training time and task performance. Breast cancer detection is currently based on the use of neural networks and their selection is an element that affects performance. In the present work, reference information on activation functions in neural networks was analyzed. Exploratory research, comprehensive reading, stepwise approach, and deduction were applied as a method. It resulted in phases of comparative evaluation inactivation functions, a quantitative and qualitative comparison of activation functions, and a prototype of neural network algorithm with activation function to detect cancer; It was concluded that the final results put as the best option to use ReLU for early detection of cancer.",

keywords = "Activation functions, Benchmarking, Cancer detection, Neural networks",

author = "Martinez, {Miguel Angel Quiroz} and Vernaza, {Josue Ricardo Borja} and Moran, {Daniel Humberto Plua} and Vazquez, {Maikel Yelandi Leyva}",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021 ; Conference date: 27-08-2021 Through 29-08-2021",

year = "2022",

doi = "10.1007/978-3-030-85540-6_110",

language = "English",

isbn = "9783030855390",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "867--873",

editor = "Tareq Ahram and Redha Taiar",

booktitle = "Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET",

address = "Germany",

}

Martinez, MAQ, Vernaza, JRB, Moran, DHP & Vazquez, MYL 2022, Benchmarking Neural Networks Activation Functions for Cancer Detection. in T Ahram & R Taiar (eds), Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET: Future Systems IHIET-FS 2021. Lecture Notes in Networks and Systems, vol. 319, Springer Science and Business Media Deutschland GmbH, pp. 867-873, 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021, Virtual, Online, 27/08/21. https://doi.org/10.1007/978-3-030-85540-6_110

Benchmarking Neural Networks Activation Functions for Cancer Detection. / Martinez, Miguel Angel Quiroz; Vernaza, Josue Ricardo Borja; Moran, Daniel Humberto Plua et al.
Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET: Future Systems IHIET-FS 2021. ed. / Tareq Ahram; Redha Taiar. Springer Science and Business Media Deutschland GmbH, 2022. p. 867-873 (Lecture Notes in Networks and Systems; Vol. 319).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Benchmarking Neural Networks Activation Functions for Cancer Detection

AU - Martinez, Miguel Angel Quiroz

AU - Vernaza, Josue Ricardo Borja

AU - Moran, Daniel Humberto Plua

AU - Vazquez, Maikel Yelandi Leyva

PY - 2022

Y1 - 2022

N2 - The choice of the most suitable activation functions for artificial neural networks significantly affects training time and task performance. Breast cancer detection is currently based on the use of neural networks and their selection is an element that affects performance. In the present work, reference information on activation functions in neural networks was analyzed. Exploratory research, comprehensive reading, stepwise approach, and deduction were applied as a method. It resulted in phases of comparative evaluation inactivation functions, a quantitative and qualitative comparison of activation functions, and a prototype of neural network algorithm with activation function to detect cancer; It was concluded that the final results put as the best option to use ReLU for early detection of cancer.

AB - The choice of the most suitable activation functions for artificial neural networks significantly affects training time and task performance. Breast cancer detection is currently based on the use of neural networks and their selection is an element that affects performance. In the present work, reference information on activation functions in neural networks was analyzed. Exploratory research, comprehensive reading, stepwise approach, and deduction were applied as a method. It resulted in phases of comparative evaluation inactivation functions, a quantitative and qualitative comparison of activation functions, and a prototype of neural network algorithm with activation function to detect cancer; It was concluded that the final results put as the best option to use ReLU for early detection of cancer.

KW - Activation functions

KW - Benchmarking

KW - Cancer detection

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85115647067&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-85540-6_110

DO - 10.1007/978-3-030-85540-6_110

M3 - Conference contribution

AN - SCOPUS:85115647067

SN - 9783030855390

T3 - Lecture Notes in Networks and Systems

SP - 867

EP - 873

BT - Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET

A2 - Ahram, Tareq

A2 - Taiar, Redha

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021

Y2 - 27 August 2021 through 29 August 2021

ER -

Martinez MAQ, Vernaza JRB, Moran DHP, Vazquez MYL. Benchmarking Neural Networks Activation Functions for Cancer Detection. In Ahram T, Taiar R, editors, Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET: Future Systems IHIET-FS 2021. Springer Science and Business Media Deutschland GmbH. 2022. p. 867-873. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-030-85540-6_110

Benchmarking Neural Networks Activation Functions for Cancer Detection

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Cite this